Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474195
M. Hussain, Thi Phuong Loan Hoang, Christian Langen
In this paper, an efficient implementation for two-dimensional non-causal Deslauriers-Dubuc discrete wavelet transformation using the lifting scheme for real-time video processing is proposed. Firstly, a two-dimensional discrete Deslauriers-Dubuc wavelet transformation for decomposition with outputs as the approximation, horizontal details, vertical details and diagonal details of the input frames and inverse discrete wavelet transformation for reconstruction of the decomposed video stream is implemented on the Simulink HDL coder platform. The method with FIFO and counter logic provides serial data to the wavelet transform module, which reduces the delay time as compared to the prior approach of the delay line [1]. The implementation addresses the solution for problems related to serial processing by non-causal wavelet filters and delay in the output frame display. Later, the Simulink model is tested on the Terasic Intel/Altera DE2i-150 board and applied to processing of real-time video supplied by a Terasic 5 MPixel digital camera at the rate of 15 frames per second.
{"title":"A Design for Two-Dimensional Non-Causal Deslauriers-Dubuc Discrete Wavelet Transformation for Real-Time Video Processing on FPGA","authors":"M. Hussain, Thi Phuong Loan Hoang, Christian Langen","doi":"10.1109/SPIN.2018.8474195","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474195","url":null,"abstract":"In this paper, an efficient implementation for two-dimensional non-causal Deslauriers-Dubuc discrete wavelet transformation using the lifting scheme for real-time video processing is proposed. Firstly, a two-dimensional discrete Deslauriers-Dubuc wavelet transformation for decomposition with outputs as the approximation, horizontal details, vertical details and diagonal details of the input frames and inverse discrete wavelet transformation for reconstruction of the decomposed video stream is implemented on the Simulink HDL coder platform. The method with FIFO and counter logic provides serial data to the wavelet transform module, which reduces the delay time as compared to the prior approach of the delay line [1]. The implementation addresses the solution for problems related to serial processing by non-causal wavelet filters and delay in the output frame display. Later, the Simulink model is tested on the Terasic Intel/Altera DE2i-150 board and applied to processing of real-time video supplied by a Terasic 5 MPixel digital camera at the rate of 15 frames per second.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114692300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474117
Jayrajsinh Zala, M. Sharma, R. Bhalerao
Pathological conditions in the knee joint can be caused by vibrations emitted in knee joint while bending or extending the leg. To detect this vibrations or to know the inner condition of the joint like softening, coarseness, breakage or it’s state of lubrication of articular cartilage surface, vibroarthrographic (VAG) signal is useful. The VAG signal is used because of fluctuating and nonlinear property which is helpful to extract the condition of knee joint. In present work on VAG signals by using the TQWT decomposition. VAG signals are partitioned into sub-band signals of distinct frequencies. There are different features of VAG Signals, fluctuating in nature like Kraskov Entropy (KE) and Signal Fractal Dimension (SFD). The performance of feature selection (FS) techniques can be validated through using the Least square support Vector machine (LS-SVM). By using LS-SVM classifier we have achieved an accuracy of 86.91%, sensitivity of 88.33%, specificity of 86.66% based on the input of 89 VAG signals.
{"title":"Tunable Q - wavelet transform based features for automated screening of knee-joint vibroarthrographic signals","authors":"Jayrajsinh Zala, M. Sharma, R. Bhalerao","doi":"10.1109/SPIN.2018.8474117","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474117","url":null,"abstract":"Pathological conditions in the knee joint can be caused by vibrations emitted in knee joint while bending or extending the leg. To detect this vibrations or to know the inner condition of the joint like softening, coarseness, breakage or it’s state of lubrication of articular cartilage surface, vibroarthrographic (VAG) signal is useful. The VAG signal is used because of fluctuating and nonlinear property which is helpful to extract the condition of knee joint. In present work on VAG signals by using the TQWT decomposition. VAG signals are partitioned into sub-band signals of distinct frequencies. There are different features of VAG Signals, fluctuating in nature like Kraskov Entropy (KE) and Signal Fractal Dimension (SFD). The performance of feature selection (FS) techniques can be validated through using the Least square support Vector machine (LS-SVM). By using LS-SVM classifier we have achieved an accuracy of 86.91%, sensitivity of 88.33%, specificity of 86.66% based on the input of 89 VAG signals.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128737340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474218
Hemashree Bordoloi, Daisy Roy, S. Nirmala
Deoxyribo Nucleic Acid (DNA) sequencing is a rapidly expanding biomedical research technology used for molecular diagnostics. It is basically a process of determining the precise order of nucleotide bases. The three unit nucleotide combinations within a DNA form codons which are related to amino acids and subsequently to proteins. One of the primary principles of disease detection is based on irregularities in the codon grouping. The focus of this work is to determine abnormalities in the codon sequence using soft computing tools and thereby provide a reliable computational mechanism for disease detection which have distinct genetic linkage.
{"title":"A Framework for Codon Based Analysis to detect abnormalities responsible for Esophagus Cancer using Soft Computing Tool","authors":"Hemashree Bordoloi, Daisy Roy, S. Nirmala","doi":"10.1109/SPIN.2018.8474218","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474218","url":null,"abstract":"Deoxyribo Nucleic Acid (DNA) sequencing is a rapidly expanding biomedical research technology used for molecular diagnostics. It is basically a process of determining the precise order of nucleotide bases. The three unit nucleotide combinations within a DNA form codons which are related to amino acids and subsequently to proteins. One of the primary principles of disease detection is based on irregularities in the codon grouping. The focus of this work is to determine abnormalities in the codon sequence using soft computing tools and thereby provide a reliable computational mechanism for disease detection which have distinct genetic linkage.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132378835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474197
Piyush Sharma, DHEERAJ KUMAR DHAKED, Sachin Saini, L. K. Tripathi, Ashish Shrivastva
Power electronics is a vast area in electrical engineering for research which includes different switching devices to control and switching of electrical machines and drives for their output, speed and torques etc. It has many applications in our everyday life such as motor drives, and power supplies for computer. The ‘current’ drawn by these devices is distorted so there is a necessity to use power factor correction converter. In this paper a comparative evaluation of different topologies of AC–DC converter is completed for Total Harmonic Distortion and enriched power factor. The model is simulated in MATLAB and their results are shown.
{"title":"Analysis of Different Converters for Reduced Total Harmonic Distortion and Improved Power Factor","authors":"Piyush Sharma, DHEERAJ KUMAR DHAKED, Sachin Saini, L. K. Tripathi, Ashish Shrivastva","doi":"10.1109/SPIN.2018.8474197","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474197","url":null,"abstract":"Power electronics is a vast area in electrical engineering for research which includes different switching devices to control and switching of electrical machines and drives for their output, speed and torques etc. It has many applications in our everyday life such as motor drives, and power supplies for computer. The ‘current’ drawn by these devices is distorted so there is a necessity to use power factor correction converter. In this paper a comparative evaluation of different topologies of AC–DC converter is completed for Total Harmonic Distortion and enriched power factor. The model is simulated in MATLAB and their results are shown.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"462 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116232305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474070
Kavita Goyal, M. Uddin, V. Jindal
The major concepts developed in the 19th and 20th centuries about the effectors of cerebral blood flow (CBF) are considered in this research paper. These effectors (arterial physiological parameters) are: arterial partial pressure of oxygen (PaO2), arterial partial pressure of carbon dioxide (PaCO2) and mean arterial blood pressure (MABP). This research is focused to evaluate the most dominant factor which is accountable for the changes in the cerebral blood flow out of these three arterial physiological parameters by using the fuzzy logic modeling. The fuzzy membership functions and their linguistic classes with their optimal range of these physiological parameters are defined with the help of literature. The evaluation of dominant factor of CBF will contribute significantly in clinical use for both health and disease.
{"title":"Fuzzy Modeling between Cerebral Blood Flow and Physiological Parameters of the Human Brain","authors":"Kavita Goyal, M. Uddin, V. Jindal","doi":"10.1109/SPIN.2018.8474070","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474070","url":null,"abstract":"The major concepts developed in the 19th and 20th centuries about the effectors of cerebral blood flow (CBF) are considered in this research paper. These effectors (arterial physiological parameters) are: arterial partial pressure of oxygen (PaO2), arterial partial pressure of carbon dioxide (PaCO2) and mean arterial blood pressure (MABP). This research is focused to evaluate the most dominant factor which is accountable for the changes in the cerebral blood flow out of these three arterial physiological parameters by using the fuzzy logic modeling. The fuzzy membership functions and their linguistic classes with their optimal range of these physiological parameters are defined with the help of literature. The evaluation of dominant factor of CBF will contribute significantly in clinical use for both health and disease.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121827042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474210
Bhat Raghavendra Ravi, S. Deepu, M. Ramesh Kini, D. S. Sumam
Fixed noise suppression techniques are generally used for speech enhancement in different low power real time systems. In this paper, we propose a modified adaptive system for classification of speech signals and noise reduction based on multi-band techniques. It involves initial identification of incoming speech segments as clean speech, speech in noise or pure noise. For the noisy speech segments, background noise classification is carried out using different wavelet-based feature sets. Noise Reduction system consists of removal of adaptive stationary noise and non-stationary noise based on classified noise type. Simulation results show that the proposed system provides optimal noise reduction and better speech quality with reduced computational complexity in adverse noisy environments.
{"title":"Wavelet based Noise Reduction Techniques for Real Time Speech Enhancement","authors":"Bhat Raghavendra Ravi, S. Deepu, M. Ramesh Kini, D. S. Sumam","doi":"10.1109/SPIN.2018.8474210","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474210","url":null,"abstract":"Fixed noise suppression techniques are generally used for speech enhancement in different low power real time systems. In this paper, we propose a modified adaptive system for classification of speech signals and noise reduction based on multi-band techniques. It involves initial identification of incoming speech segments as clean speech, speech in noise or pure noise. For the noisy speech segments, background noise classification is carried out using different wavelet-based feature sets. Noise Reduction system consists of removal of adaptive stationary noise and non-stationary noise based on classified noise type. Simulation results show that the proposed system provides optimal noise reduction and better speech quality with reduced computational complexity in adverse noisy environments.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123872274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474163
Surajit Deka, K. K. Sarma
In this paper, we have considered the broadcasting of a memoryless bivariate Gaussian source over a Gaussian broadcast channel with respect to bandwidth compression. We have analysed the performance of a hybrid digital-analog (HDA) coding system in combination with joint source channel coding (JSCC) to measure the distortion regions. The transmission advantages due to the combination of both the analog and digital techniques, a class of HDA schemes that yields better performance in distortion is discussed. The performance of source and channel coding for the possible better outcome of the system is measured by employing Wyner-Ziv and Costa coding. In our model, we have considered the upper layer to be a combination of a hybrid layer in the sense of both the analog and digital processing is done. This is executed in presence of quantization error and performance of the system is measured with two conditions: 1) HDA scheme with quantization scaling factor α = 0, i.e. the input of the channel have only the analog information which is considered as the scaled quantization error βS 2) The analog information from the first layer S is suppressed by setting error scaling factor β = 0 and 3) Inclusion of recursive mode with JSCC in each of the three layers for the possible better outcome is considered here.
{"title":"Joint Source Channel Coding with Bandwidth Compression","authors":"Surajit Deka, K. K. Sarma","doi":"10.1109/SPIN.2018.8474163","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474163","url":null,"abstract":"In this paper, we have considered the broadcasting of a memoryless bivariate Gaussian source over a Gaussian broadcast channel with respect to bandwidth compression. We have analysed the performance of a hybrid digital-analog (HDA) coding system in combination with joint source channel coding (JSCC) to measure the distortion regions. The transmission advantages due to the combination of both the analog and digital techniques, a class of HDA schemes that yields better performance in distortion is discussed. The performance of source and channel coding for the possible better outcome of the system is measured by employing Wyner-Ziv and Costa coding. In our model, we have considered the upper layer to be a combination of a hybrid layer in the sense of both the analog and digital processing is done. This is executed in presence of quantization error and performance of the system is measured with two conditions: 1) HDA scheme with quantization scaling factor α = 0, i.e. the input of the channel have only the analog information which is considered as the scaled quantization error βS 2) The analog information from the first layer S is suppressed by setting error scaling factor β = 0 and 3) Inclusion of recursive mode with JSCC in each of the three layers for the possible better outcome is considered here.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125007858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474176
Kshitij Kala, Akhilesh Dwivedi, Janmejay Pant, Senam Pandey, Vertika Kandpal, R. P. Pant
In this paper, we have developed an algorithm that proposes advance and novice security mechanism that can defend any kind of attacks and is advantageous over the other existing algorithms that are currently being used in security areas like email and web-based security applications. This algorithm is based on the concept of time in analog clock. The most powerful feature of this algorithm is 10506 (permutation of substitution clock). We implemented this algorithm in python. And after verification and validation we found out that it is impossible to crack by any kind of tool in existence. We are looking forward to use this algorithm in various applications.
{"title":"A Novice Encryption Technique using Substitution Clock and Time in It (SCT)","authors":"Kshitij Kala, Akhilesh Dwivedi, Janmejay Pant, Senam Pandey, Vertika Kandpal, R. P. Pant","doi":"10.1109/SPIN.2018.8474176","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474176","url":null,"abstract":"In this paper, we have developed an algorithm that proposes advance and novice security mechanism that can defend any kind of attacks and is advantageous over the other existing algorithms that are currently being used in security areas like email and web-based security applications. This algorithm is based on the concept of time in analog clock. The most powerful feature of this algorithm is 10506 (permutation of substitution clock). We implemented this algorithm in python. And after verification and validation we found out that it is impossible to crack by any kind of tool in existence. We are looking forward to use this algorithm in various applications.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129558333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474235
Ghanishtha Narang, Mona Aggarwal, H. Kaushal, Swaran Ahuja
Free Space Optical (FSO) communication system is known for its high capacity, very large bandwidth, high directivity, non-licensed spectrum and many more advantages. The main issues in any communication system are security and privacy. Although FSO communication is more secure than Radio Frequency (RF) communication system, however, FSO communication still suffer from security threats due to tapping or beam spillage issues. The use of chaotic signals in communication leads to a revolution in the history of secure transmission of information. Therefore, in this manuscript, we aim to improve the security of FSO communication system taking Gamma-Gamma turbulence model using Differential Chaos Shift Keying (DCSK). The performance of the proposed chaotic FSO system is studied taking into consideration different turbulence conditions and analytical expression of probability of error has been derived.
{"title":"Error probability analysis of FSO Communication System using Differential Chaos Shift Keying","authors":"Ghanishtha Narang, Mona Aggarwal, H. Kaushal, Swaran Ahuja","doi":"10.1109/SPIN.2018.8474235","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474235","url":null,"abstract":"Free Space Optical (FSO) communication system is known for its high capacity, very large bandwidth, high directivity, non-licensed spectrum and many more advantages. The main issues in any communication system are security and privacy. Although FSO communication is more secure than Radio Frequency (RF) communication system, however, FSO communication still suffer from security threats due to tapping or beam spillage issues. The use of chaotic signals in communication leads to a revolution in the history of secure transmission of information. Therefore, in this manuscript, we aim to improve the security of FSO communication system taking Gamma-Gamma turbulence model using Differential Chaos Shift Keying (DCSK). The performance of the proposed chaotic FSO system is studied taking into consideration different turbulence conditions and analytical expression of probability of error has been derived.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129716024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474279
A. Savakis, Aadeesh Milind Shringarpure
We present a method that estimates the scene background in videos by utilizing semantic segmentation to extract foreground objects, such as people or cars, and stitching background regions to reconstruct the background. Inspired by recent developments in deep learning, we utilize semantic segmentation based on Conditional Random Field as Recurrent Neural Networks (CRF as RNN) to detect the regions of important objects in each frame and generate a foreground-background map. We use these segmentation maps to extract the background regions from each frame and then stitch them over consecutive frames to obtain the full background for the video sequence. Our foreground/background estimation approach has potential applications in change detection, video surveillance, video compression and video privacy. We illustrate the effectiveness of our method on example videos from the Change Detection (CDNET) dataset.
本文提出了一种利用语义分割提取前景对象(如人或车)，并拼接背景区域重建背景的视频场景背景估计方法。受深度学习最新发展的启发，我们利用基于条件随机场的语义分割作为递归神经网络(CRF as RNN)来检测每帧中重要物体的区域，并生成前景-背景图。我们使用这些分割映射从每帧中提取背景区域，然后将它们拼接到连续的帧中，以获得视频序列的完整背景。我们的前景/背景估计方法在变化检测、视频监控、视频压缩和视频隐私方面具有潜在的应用前景。我们对来自变化检测(CDNET)数据集的示例视频演示了我们的方法的有效性。
{"title":"Semantic Background Estimation in Video Sequences","authors":"A. Savakis, Aadeesh Milind Shringarpure","doi":"10.1109/SPIN.2018.8474279","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474279","url":null,"abstract":"We present a method that estimates the scene background in videos by utilizing semantic segmentation to extract foreground objects, such as people or cars, and stitching background regions to reconstruct the background. Inspired by recent developments in deep learning, we utilize semantic segmentation based on Conditional Random Field as Recurrent Neural Networks (CRF as RNN) to detect the regions of important objects in each frame and generate a foreground-background map. We use these segmentation maps to extract the background regions from each frame and then stitch them over consecutive frames to obtain the full background for the video sequence. Our foreground/background estimation approach has potential applications in change detection, video surveillance, video compression and video privacy. We illustrate the effectiveness of our method on example videos from the Change Detection (CDNET) dataset.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129787809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：